{"id":"W3018974563","doi":"10.1186/s12911-020-1089-0","title":"Development and validation of data quality rules in administrative health data using association rule mining","year":2020,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Health; University of Calgary; Alberta Health Services","funders":"Canadian Institutes of Health Research","keywords":"Association rule learning; Data mining; Coding (social sciences); Data quality; Variance (accounting); Computer science; Delphi method; Health informatics; Quality (philosophy); Data set; Medicine; Statistics; Artificial intelligence; Operations management; Mathematics; Public health; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01199789,0.0001178296,0.0004450839,0.0001099379,0.0003948388,0.00002933746,0.0003193462,0.0002284595,0.00006893681],"category_scores_gemma":[0.009177584,0.00009878304,0.000009563895,0.0002026405,0.00003816797,0.0007834281,0.0009935513,0.0004502167,0.000008672447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001302532,"about_ca_system_score_gemma":0.002216271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004528986,"about_ca_topic_score_gemma":0.0001805204,"domain_scores_codex":[0.9953298,0.0003320405,0.002702384,0.0001935976,0.001124416,0.0003177659],"domain_scores_gemma":[0.9933658,0.004283621,0.00150513,0.0003552889,0.0001068917,0.0003832651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002571181,0.00005517416,0.09775738,0.007069894,0.00002411733,0.00000160155,0.06270776,0.00005203686,0.000001715057,0.001293298,0.003151675,0.8276283],"study_design_scores_gemma":[0.001401745,0.00004328204,0.01235211,0.003165245,0.000008555775,0.00000191445,0.0218499,0.9565831,0.000002364706,0.0002808837,0.00416752,0.0001434235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6852953,0.0001178931,0.3133833,0.0003942585,0.0001035154,0.0003006448,0.00008831116,0.00001963436,0.0002971018],"genre_scores_gemma":[0.2618732,0.0002085978,0.7338589,0.003439418,0.0001031567,0.000005544439,0.0005010951,0.000007532842,0.00000254236],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.956531,"threshold_uncertainty_score":0.9991685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7776327660639315,"score_gpt":0.6048172612575257,"score_spread":0.1728155048064058,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}